{"id":"https://openalex.org/W3035645517","doi":"https://doi.org/10.24963/ijcai.2020/282","title":"Variational Learning of Bayesian Neural Networks via Bayesian Dark Knowledge","display_name":"Variational Learning of Bayesian Neural Networks via Bayesian Dark Knowledge","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035645517","doi":"https://doi.org/10.24963/ijcai.2020/282","mag":"3035645517"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/282","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/282","pdf_url":"https://www.ijcai.org/proceedings/2020/0282.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0282.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083758519","display_name":"Gehui Shen","orcid":"https://orcid.org/0000-0002-2457-3810"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gehui Shen","raw_affiliation_strings":["Peking University","Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329897","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-0319-9786"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Peking University","Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060171279","display_name":"Zhihong Deng","orcid":"https://orcid.org/0000-0003-0226-0626"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihong Deng","raw_affiliation_strings":["Peking University","Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060171279"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2037","last_page":"2043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.7722427845001221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6278636455535889},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5782032608985901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5469555854797363},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5468130707740784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5354803800582886},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5186985731124878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34074029326438904}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.7722427845001221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6278636455535889},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5782032608985901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5469555854797363},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5468130707740784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5354803800582886},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5186985731124878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34074029326438904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/282","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/282","pdf_url":"https://www.ijcai.org/proceedings/2020/0282.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/282","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/282","pdf_url":"https://www.ijcai.org/proceedings/2020/0282.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035645517.pdf","grobid_xml":"https://content.openalex.org/works/W3035645517.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W601603264","https://openalex.org/W1567512734","https://openalex.org/W1592410721","https://openalex.org/W1673923490","https://openalex.org/W1821462560","https://openalex.org/W1872312298","https://openalex.org/W1945616565","https://openalex.org/W1959608418","https://openalex.org/W2047229728","https://openalex.org/W2108677974","https://openalex.org/W2111051539","https://openalex.org/W2144193737","https://openalex.org/W2164411961","https://openalex.org/W2165652770","https://openalex.org/W2167433878","https://openalex.org/W2528914598","https://openalex.org/W2592505114","https://openalex.org/W2599043568","https://openalex.org/W2600383743","https://openalex.org/W2626967530","https://openalex.org/W2809702612","https://openalex.org/W2949677752","https://openalex.org/W2951105989","https://openalex.org/W2951654389","https://openalex.org/W2951786554","https://openalex.org/W2963207607","https://openalex.org/W2964059111","https://openalex.org/W2964153729","https://openalex.org/W2964212410","https://openalex.org/W2964282813","https://openalex.org/W4300485191","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W3087071515","https://openalex.org/W4283077537","https://openalex.org/W2999603699","https://openalex.org/W2464065341","https://openalex.org/W2947536360","https://openalex.org/W3086697448","https://openalex.org/W2968689489","https://openalex.org/W4302573481","https://openalex.org/W2505308168","https://openalex.org/W2963960970"],"abstract_inverted_index":{"Bayesian":[0,40,115,122],"neural":[1,23,61],"networks":[2],"(BNNs)":[3],"have":[4],"received":[5],"more":[6,8,68],"and":[7,31,70,186],"attention":[9],"because":[10],"they":[11],"are":[12,35,158],"capable":[13,167],"of":[14,60,90,106,137,152,168,183],"modeling":[15,169],"epistemic":[16,170],"uncertainty":[17,187],"which":[18,130],"is":[19,45,51,67],"hard":[20],"for":[21,39],"conventional":[22],"networks.":[24],"Markov":[25],"chain":[26],"Monte":[27],"Carlo":[28],"(MCMC)":[29],"methods":[30,38,93,143,176],"variational":[32,76,101,114,139],"inference":[33],"(VI)":[34],"two":[36,92],"mainstream":[37],"deep":[41],"learning.":[42],"The":[43,64],"former":[44],"effective":[46],"but":[47,160],"its":[48,79],"storage":[49],"cost":[50],"prohibitive":[52],"since":[53],"it":[54],"has":[55],"to":[56,86],"save":[57],"many":[58],"samples":[59,97],"network":[62],"parameters.":[63],"latter":[65],"method":[66,129,180],"time":[69],"space":[71,150],"efficient,":[72],"however":[73],"the":[74,88,104,135,149,153],"approximate":[75,100],"posterior":[77,133,165],"limits":[78],"performance.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84,111,120],"aim":[85],"combine":[87],"advantages":[89],"above":[91],"by":[94],"distilling":[95],"MCMC":[96,132],"into":[98],"an":[99,107],"posterior.":[102],"On":[103],"basis":[105],"existing":[108,178],"distillation":[109,128,179],"technique":[110],"first":[112],"propose":[113,121],"dark":[116,123],"knowledge":[117],"method.":[118],"Moreover,":[119],"prior":[124,136],"knowledge,":[125],"a":[126,138,163],"novel":[127],"considers":[131],"as":[134],"BNN.":[140],"Two":[141],"proposed":[142],"both":[144],"not":[145],"only":[146],"can":[147],"reduce":[148],"overhead":[151],"teacher":[154],"model":[155],"so":[156],"that":[157],"scalable,":[159],"also":[161],"maintain":[162],"distilled":[164],"distribution":[166],"uncertainty.":[171],"Experimental":[172],"results":[173],"manifest":[174],"our":[175],"outperform":[177],"in":[181],"terms":[182],"predictive":[184],"accuracy":[185],"modeling.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}